fp-recovery

fp-recovery is a skill for Claude Code from navapbc/digital-service-orchestra. It costs 118 tokens per session (1,495 once invoked), scanned A, original, Apache-2.0.

A manual review workflow for cases where an automated code review in continuous integration blocks a pull request on a suspected false positive. A false positive is a warning that does not apply to the changed code.

In plain words
What is it for?
Use it to re-review a blocked pull request, assess the reported finding, and issue merge clearance when no critical problems remain.
Why use it?
It provides an escalation path when the automated finding appears incorrect while preserving checks for serious remaining problems. CI is the automated process that tests and reviews changes before merging.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

Good fit Use it to re-review a blocked pull request, assess the reported finding, and issue merge clearance when no critical problems remain.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add navapbc/digital-service-orchestra
Claude Code
/plugin install dso

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fp-recovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/fp-recovery/github.svg)](https://agentmods.dev/skills/navapbc/digital-service-orchestra/fp-recovery)
Your own site
<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/fp-recovery"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/fp-recovery/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fp-recovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/fp-recovery"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/fp-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,495 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.01495
Opus 5 $0.00059 $0.00747
Sonnet 5 $0.00024 $0.00299
Haiku 4.5 $0.00012 $0.00150

Measured 9d ago against content hash 245e6c56bc6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fp-recovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/dso/skills/fp-recovery/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FP Recovery — Manual Review Escalation

Shallow entry point for the FP-recovery workflow. Loads and executes ${CLAUDE_PLUGIN_ROOT}/docs/workflows/FP-RECOVERY-WORKFLOW.md inline.

When to invoke

CI llm-review (ci.yml) has reported failure AND the engineer believes the blocking finding is a false positive. All other required checks must pass (or be filed as known intermittent bugs). See FP-RECOVERY-WORKFLOW.md "When to invoke" for the full precondition list.

Eligible finding types — FP-recovery may be invoked for findings of any of these types when the engineer believes the finding is a false positive:

  • Code-level findings (logic, security, correctness, style)
  • DESIGN.md lint findings — violations flagged by the check-design-lint.sh hook or equivalent design-doc linter (e.g., missing required sections, disallowed heading format, broken cross-references to ticket IDs). These are eligible when the engineer can demonstrate the design document is structurally correct and the linter rule is misapplied for the specific context.

Common false-positive patterns for DESIGN.md lint findings:

  • The linter flags a missing required section that is intentionally omitted because it is not applicable to the change type (e.g., no "Data Model" section for a UI-only change).
  • A ticket ID cross-reference is flagged as broken, but the ticket exists and the ID format is correct (linter regex mismatch).
  • The linter rejects a heading because of an extra trailing space or Unicode em-dash that is visually indistinguishable from a standard ASCII hyphen.
  • A newly added DESIGN.md section is flagged as unknown because the linter's allowed-section list has not been updated.

Finding format for DESIGN.md lint findings — when invoking FP-recovery for a DESIGN.md lint finding, the engineer must supply:

  1. The exact linter rule name or error message (copy from CI log).
  2. The specific line(s) in DESIGN.md that triggered the finding.
  3. A concise rationale explaining why the finding is a false positive (not just "it looks fine").

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 69 lines · 118 tokens per session scan A 245e6c56bc6e

Subscribe to this mod's changes

fp-recovery is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 118 tokens to every session and 1,495 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

gsd-ns-review

Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.

open-gsd/gsd-core · 16 tokens

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

gitnexus

A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.

hashgraph-online/awesome-codex-plugins · 58 tokens

cleanup-code-inspections

Reduce technical debt and improve code quality by systematically resolving static analysis warnings.

flutter/flutter-intellij · 19 tokens

sonarqube-mcp

Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…

giuseppe-trisciuoglio/developer-kit · 127 tokens